When using Acoustic Emission (AE) technologies, tensile and compressive tests can provide a detector for material deformation. In this paper improvements are made to standardise calibration techniques. AE signatures were evaluated from various calibration sources based on the energy from the first harmonic (dominant energy band) [1][2]. The work presented here provides further, valuable knowledge to both the manufacturing and structural health monitoring research communities. The effects of AE against its calibration identity are investigated: where signals are correlated to the average energy and distance of the detected phenomena. Five sources of calibration would be required in order to calculate an average amount. AE evaluated by a Neural Network (NN) regression classification technique identifies how far the malformation has progressed (in terms of energy/force) during material transformation. A genetic-fuzzy-c-clustering classifier was used as the 2nd classification technique to verify the classifications of the NN. This calibration method can be used for legislation purposes when either machining or operating. In summary this paper presents a new method of AE calibration through the correlation of AE and force/distance measurements.

This content is only available via PDF.
You do not currently have access to this content.